---
title: fish-speech-1
canonical_url: "https://www.modelscope.ai/models/fishaudio/fish-speech-1"
md_url: "https://www.modelscope.ai/models/fishaudio/fish-speech-1.md"
repository: fishaudio/fish-speech-1
last_updated: 2025-12-04
license: cc-by-nc-sa-4.0
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
library_name:
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
  - ja
downloads: 125
stars: 0
tags:
  - text-to-speech
---

# fish-speech-1

> fish-speech-1 - An open-source model by fishaudio on ModelScope. Fish Speech V1 is a leading text-to-speech (TTS) model trained on 150k hours of English, Chinese, and Japanese audio data.

fishaudio/fish-speech-1 is a text-to-speech model on ModelScope. licensed under cc-by-nc-sa-4.0.

- **Repository**: fishaudio/fish-speech-1
- **License**: cc-by-nc-sa-4.0
- **Tasks**: text-to-speech
- **Tags**: text-to-speech
- **Downloads**: 125
- **Stars**: 0
- **Last updated**: 2025-12-04

Source: https://www.modelscope.ai/models/fishaudio/fish-speech-1

---

# Fish Speech V1

<a target="_blank" href="https://huggingface.co/spaces/fishaudio/fish-speech-1">
  <img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-sm.svg" alt="Open in HuggingFace"/>
</a>


**Fish Speech V1** is a leading text-to-speech (TTS) model trained on 150k hours of English, Chinese, and Japanese audio data. 

Please refer to [Fish Speech Github](https://github.com/fishaudio/fish-speech) for more info.  
Demo available at [Huggingface Spaces](https://huggingface.co/spaces/fishaudio/fish-speech-1) and [Fish Audio](https://fish.audio/text-to-speech/).

## Citation

If you found this repository useful, please consider citing this work:

```
@misc{fish-speech-v1,
  author = {Shijia Liao, Tianyu Li},
  title = {Fish Speech V1},
  year = {2024},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/fishaudio/fish-speech}}
}
```

## License

This model is permissively licensed under the BY-CC-NC-SA-4.0 license.
The source code is released under BSD-3-Clause license.